{"id":19449380,"url":"https://github.com/aavache/mlx-resnet","last_synced_at":"2025-10-09T06:32:43.275Z","repository":{"id":211630274,"uuid":"729601834","full_name":"Aavache/mlx-resnet","owner":"Aavache","description":"ResNet implementation with the MLX, Apple's DL framework.","archived":false,"fork":false,"pushed_at":"2023-12-09T18:44:37.000Z","size":7,"stargazers_count":8,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-25T03:37:09.044Z","etag":null,"topics":["apple","computer-vision","deep-learning","machine-learning","mlx","mnist","resnet"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Aavache.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-12-09T18:41:12.000Z","updated_at":"2025-04-03T04:56:04.000Z","dependencies_parsed_at":"2023-12-09T20:46:55.475Z","dependency_job_id":null,"html_url":"https://github.com/Aavache/mlx-resnet","commit_stats":null,"previous_names":["aavache/mlx-resnet"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Aavache/mlx-resnet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aavache%2Fmlx-resnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aavache%2Fmlx-resnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aavache%2Fmlx-resnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aavache%2Fmlx-resnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Aavache","download_url":"https://codeload.github.com/Aavache/mlx-resnet/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aavache%2Fmlx-resnet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000825,"owners_count":26082950,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["apple","computer-vision","deep-learning","machine-learning","mlx","mnist","resnet"],"created_at":"2024-11-10T16:32:12.726Z","updated_at":"2025-10-09T06:32:43.256Z","avatar_url":"https://github.com/Aavache.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 style=\"text-align: center;\"\u003e🍏 MLX - ResNet 🍏\u003c/h1\u003e\n\nResNet implementation with the [MLX](https://github.com/ml-explore/mlx), Apple's deep learning framework.\n\nDrop a ⭐️!!\n\n## MNIST with ResNet18\n\nHere the logs when training with ResNet18 (no tuning at all) for couple epochs:\n\n```sh\nEpoch: 0 | Iter: 0 | Loss: 2.550\nEpoch: 0 | Iter: 50 | Loss: 1.813\nEpoch: 0 | Iter: 100 | Loss: 1.241\nEpoch: 0 | Iter: 150 | Loss: 0.965\nEpoch: 0 | Iter: 200 | Loss: 0.741\nEpoch 0: Test accuracy 0.671\nEpoch: 1 | Iter: 0 | Loss: 1.039\nEpoch: 1 | Iter: 50 | Loss: 0.491\nEpoch: 1 | Iter: 100 | Loss: 0.471\nEpoch: 1 | Iter: 150 | Loss: 0.497\nEpoch: 1 | Iter: 200 | Loss: 0.377\nEpoch 1: Test accuracy 0.876\nEpoch: 2 | Iter: 0 | Loss: 0.425\nEpoch: 2 | Iter: 50 | Loss: 0.367\nEpoch: 2 | Iter: 100 | Loss: 0.334\nEpoch: 2 | Iter: 150 | Loss: 0.323\nEpoch: 2 | Iter: 200 | Loss: 0.346\nEpoch 2: Test accuracy 0.916\nEpoch: 3 | Iter: 0 | Loss: 0.334\nEpoch: 3 | Iter: 50 | Loss: 0.308\nEpoch: 3 | Iter: 100 | Loss: 0.282\nEpoch: 3 | Iter: 150 | Loss: 0.230\nEpoch: 3 | Iter: 200 | Loss: 0.173\nEpoch 3: Test accuracy 0.902\nEpoch: 4 | Iter: 0 | Loss: 0.282\nEpoch: 4 | Iter: 50 | Loss: 0.184\nEpoch: 4 | Iter: 100 | Loss: 0.268\nEpoch: 4 | Iter: 150 | Loss: 0.205\nEpoch: 4 | Iter: 200 | Loss: 0.246\nEpoch 4: Test accuracy 0.932\n```\n\n\n## Future updates\n\n* `dilation` and `groups` features in convolutional layers is missing ([issue](https://github.com/ml-explore/mlx/issues/100) created). More recent ResNet requires this parameters.\n* Batch norm is also missing.\n* No pretrained weights.\n\n## Contribute\n\nFeel free to create issues and PRs :)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faavache%2Fmlx-resnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faavache%2Fmlx-resnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faavache%2Fmlx-resnet/lists"}